© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24047
    Prev
    Next
    INDEX
    Explanations

    NO, CO, TC, PS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ander
    -0.08
     possibly
    -0.07
    åı¯èĥ½
    -0.07
    owers
    -0.07
     probably
    -0.07
    ebro
    -0.06
    åĬłåĪĨ
    -0.06
    举åŁİ
    -0.06
    çīĩ
    -0.06
    ä»»
    -0.06
    POSITIVE LOGITS
    estes
    0.08
    zeh
    0.07
    éĺģ
    0.07
    ç¾ŀ
    0.07
    /stretch
    0.07
    åĸľéĹ»
    0.07
    =json
    0.07
    åł¡
    0.07
    ç»ĻäºĨä»ĸ
    0.07
    ikin
    0.07
    Activations Density 0.004%

    No Known Activations